Introduction. Diabetes mellitus (DM) is a highly prevalent disease worldwide. It has been associated with an important morbimortality due to its complications and sometimes as a result of adverse events related to treatment. Insulin pump therapy (IPT) is one of the options used to control this disease and reduces one of the most frequent complication associated with treatment: hypoglycemia, which has also a great impact on life quality and clinical status of patients. Materials and Methods. A descriptive and retrospective study was performed including patients treated and followed by the department of endocrinology from a high-complexity university hospital in Cali, Colombia, between 2012 and 2017. Patients were on IPT and continuous glucose monitoring (CGM): MiniMed Paradigm® Veo™ Insulin Pump (Medtronic®) and MiniMed 640G Insulin Pump-Enlite™ Sensor (Medtronic®). Presentation of hypoglycemia and variables associated with its development were evaluated. Results. 51 patients were included. The main indication for IPT initiation was the report of hypoglycemic episodes and inappropriate metabolic control. Initiation of IPT was related with a decrease in glycosylated hemoglobin (HbA1c) and also a decrease in severe hypoglycemic events and hospitalization due to hypoglycemia. The risk factors linked with clinically significant hypoglycemia were male gender, and standard deviation of glucose measures calculated by CGM. A diminished glomerular filtration rate (GFR) (<60 mL/min/1.73 m2) was correlated with higher risk of severe hypoglycemia. Conclusion. IPT with CGM is a useful strategy in the management of patients with DM; it is associated with a reduction of adverse hypoglycemic events and hospitalizations due to hypoglycemia.

Riedel’s thyroiditis is a rare entity consisting of a fibrotic process of the thyroid which can generate gland destruction, infiltration of cervical structures and even airway obstruction. It has been associated with systemic fibrotic disorders, autoimmune diseases, and more recently with spectrum of diseases related to excess of Immunoglobulin G type 4 (IgG4). Two cases of Riedel’s thyroiditis by IgG4, confirmed by immunohistochemistry and was managed surgically with favorable results during the follow-up time, are presented. These case descriptions highlight the diagnostic challenge of this disease, describe the response with surgical management, and make a brief update on the subject.

Artificial intelligence techniques have been positioned in the resolution of problems in various areas of healthcare. Clinical decision support systems developed from this technology have optimized the healthcare of patients with chronic diseases through mobile applications. In this study, several models based on this methodology have been developed to calculate the basal insulin dose in patients with type I diabetes using subcutaneous insulin infusion pumps. Methods. A pilot experimental study was performed with data from 56 patients with type 1 diabetes who used insulin infusion pumps and underwent continuous glucose monitoring. Several models based on artificial intelligence techniques were developed to analyze glycemic patterns based on continuous glucose monitoring and clinical variables in order to estimate the basal insulin dose. We used neural networks (NNs), Bayesian networks (BNs), support vector machines (SVMs), and random forests (RF). We then evaluated the agreement between predicted and actual values using several statistical error measurements: mean absolute error (MAE), mean square error (MSE), root-mean-square error (RMSE), Pearson’s correlation coefficient (R), and determination coefficient (R2). Results. Twenty-four different models were obtained, one for each hour of the day, with each chosen technique. Correlation coefficients obtained with RF, SVMs, NNs, and BNs were 0.9999, 0.9921, 0.0303, and 0.7754, respectively. The error increased between 06:00 and 07:00 and between 13:00 and 17:00. Conclusions. The performance of the RF technique was excellent and got very close to the actual values. Intelligence techniques could be used to predict basal insulin dose. However, it is necessary to explore the validity of the results and select the target population. Models that allow for more accurate levels of prediction should be further explored.